# Spherical formulation of geometric motion segmentation constraints in fisheye cameras

arXiv: https://arxiv.org/abs/2104.12404 · HTML: https://mlsanity.com/paper/2104.12404/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 29 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 5 of 5)

- [Fast Optical Flow using Dense Inverse Search](https://mlsanity.com/paper/1603.03590/) (2016)
- [FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving](https://mlsanity.com/paper/1908.11789/) (2019)
- [Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation](https://mlsanity.com/paper/1902.09103/) (2019)
- [Robust and Efficient Relative Pose with a Multi-camera System for Autonomous Vehicle in Highly Dynamic Environments](https://mlsanity.com/paper/1605.03689/) (2016)
- [Spherical formulation of moving object geometric constraints for monocular fisheye cameras](https://mlsanity.com/paper/2003.03262/) (2020)

## Built on by (most cited first, 4 of 4)

- [Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges](https://mlsanity.com/paper/2205.13281/) (2022)
- [Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework](https://mlsanity.com/paper/2212.04111/) (2022)
- [Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges](https://mlsanity.com/paper/2402.12041/) (2024)
- [2.5D Vehicle Odometry Estimation](https://mlsanity.com/paper/2111.08398/) (2021)

## Abstract (arXiv)

We introduce a visual motion segmentation method employing spherical geometry for fisheye cameras and automoated driving. Three commonly used geometric constraints in pin-hole imagery (the positive height, positive depth and epipolar constraints) are reformulated to spherical coordinates, making them invariant to specific camera configurations as long as the camera calibration is known. A fourth constraint, known as the anti-parallel constraint, is added to resolve motion-parallax ambiguity, to support the detection of moving objects undergoing parallel or near-parallel motion with respect to the host vehicle. A final constraint constraint is described, known as the spherical three-view constraint, is described though not employed in our proposed algorithm. Results are presented and analyzed that demonstrate that the proposal is an effective motion segmentation approach for direct employment on fisheye imagery.